Applying the logistic regression in electrical impedance tomography to analyze conductivity of the examined objects

2020 ◽  
pp. 1-18
Author(s):  
Tomasz Rymarczyk ◽  
Edward Kozłowski ◽  
Paweł Tchórzewski ◽  
Grzegorz Kłosowski ◽  
Przemysław Adamkiewicz
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Image Reconstruction ◽  
Electrical Impedance Tomography ◽  
Spatial Data ◽  
High Speed ◽  
Electrical Impedance ◽  
Numerical Models ◽  
Impedance Tomography ◽  
Input Variables

The article presents machine learning methods in the field of reconstruction of tomographic images. The presented research results show that electric tomography makes it possible to analyze objects without interfering with them. The work focused mainly on electrical impedance tomography and image reconstruction using deterministic methods and machine learning, reconstruction results were compared and various numerical models were used. The main advantage of the presented solution is the ability to analyze spatial data and high speed of processing. The implemented algorithm based on logistic regression is promising in image reconstruction. In addition, the elastic net method was used to solve the problem of selecting input variables in the regression model.

scholarly journals Intelligent System for Analysis and Monitoring of Flood Embankments Based on Electrical Impedance Tomography, Machine Learning and Internet of Things

2018 ◽  
Author(s):  
Tomasz Rymarczyk ◽  
Edward Kozłowski ◽  
Grzegorz Kłosowski
Keyword(s):  
Machine Learning ◽  
Image Reconstruction ◽  
Internet Of Things ◽  
Electrical Impedance Tomography ◽  
Electrical Impedance ◽  
Visual Analysis ◽  
Intelligent System ◽  
Test System ◽  
Machine Learning Algorithms ◽  
Impedance Tomography

The article presents a non-destructive test system based on electrical impedance tomography for monitoring flood embankments. The technology of cyber-physical systems and the Internet of Things with the use of electrical impedance tomography enables real-time monitoring of flood embankments. This solution provides a visual analysis of damage and leaks, which allows for quick and effective intervention and possible prevention of danger. A dedicated solution based on the IT structure, dedicated laboratory models and a dedicated measurement system with various types of sensors and machine learning algorithms for image reconstruction has been developed. The system includes specialized intelligent devices for tomographic measurements. The application contains the analysis of anomalies occurring in the structure of the object as a result of damage or danger and breaking the shaft during the flood. The presented solution enables ongoing monitoring of objects by collecting measurement results, forecasts and simulations. The main advantage of the proposed system is the spatial ability to analyse shafts, high accuracy of imaging and high speed of data processing. The use of tomographic techniques in conjunction with image reconstruction algorithms allow for non-invasive and very accurate spatial assessment of humidity and damages of flood embankments. The presented results show the effectiveness of the presented research.

Sign in / Sign up

Export Citation Format

Share Document